Simulating Bosonic Fractional Quantum Hall States using Deep Learning

We explore a machine learning-inspired variational framework for investigating strongly correlated phases in bosonic fractional quantum Hall systems. By leveraging a self-attention-based neural quantum state architecture, we aim to capture the complex entanglement structure and non-local correlations inherent to topologically ordered phases. Our approach opens a promising pathway toward scalable modelling of nontrivial quantum many-body phenomena.